SavedAdd your journal

Journals / Tarım Bilimleri Dergisi / 2023 / Cilt: 29 - Sayı: 2

Evaluation of Image Processing Technique on Quality Properties of Chickpea Seeds (Cicer arietinum L.) Using Machine Learning Algorithms

İhsan Serkan VAROL
Necati ÇETİN
Halil KIRNAK
Pages
427–442
Publication Date
2023-03-31
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results showed that multilayer perceptron (MLP) had the greatest correlation coefficients for mass (0.9997), chroma (0.9998) hue angle (0.9998) and color index (0.9992).

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Chickpea is an important edible legume consumed worldwide because of rich nutrient composition.
📊
Key Findings & Data:In this study, effects of seven different irrigation treatments (I1-rainfed, I2-pre-flowering single irrigation, I3-beginning of flowering single irrigation, I4-50% pod set single irrigation, I5-irrigation at 50% flowering and 50% pod fill, I6-irrigation before flowering and at 50% pod set, I7-full irrigation) on size, shape, mass, and color properties of chickpea seeds were investigated, and machine learning algorithms were used to estimate mass and color attributes of chickpea seeds.
💡
Conclusion & Impact:The results showed that multilayer perceptron (MLP) had the greatest correlation coefficients for mass (0.9997), chroma (0.9998) hue angle (0.9998) and color index (0.9992).
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Chickpea · Mass · Color

Abstract

Chickpea is an important edible legume consumed worldwide because of rich nutrient composition. The physical parameters of chickpea are crucial attributes for design of processing and classification systems. In this study, effects of seven different irrigation treatments (I1-rainfed, I2-pre-flowering single irrigation, I3-beginning of flowering single irrigation, I4-50% pod set single irrigation, I5-irrigation at 50% flowering and 50% pod fill, I6-irrigation before flowering and at 50% pod set, I7-full irrigation) on size, shape, mass, and color properties of chickpea seeds were investigated, and machine learning algorithms were used to estimate mass and color attributes of chickpea seeds. In terms of physical attributes, the best results were obtained in I1 and I5 irrigation treatments. According to the findings, among the irrigation treatments, I5 had the greatest mass, volume, geometric mean diameter, projected area with the values of 0.50 g, 394.86 cm3, 9.10 mm and 65.03 mm2, respectively. In addition, I1 had the highest shape index and elongation as 1.33 and 1.34, respectively. The results showed that multilayer perceptron (MLP) had the greatest correlation coefficients for mass (0.9997), chroma (0.9998) hue angle (0.9998) and color index (0.9992). The MLP yielded better outcomes than random forest for both mass and color estimation. Additionally, single or couple irrigation treatment at different physiological stages instead of full irrigation treatment might be sufficient to improve the physical attributes of chickpea.

🔖

Cite This Article

VAROL, İ. S., ÇETİN, N., KIRNAK, H. (2023). Evaluation of Image Processing Technique on Quality Properties of Chickpea Seeds (Cicer arietinum L.) Using Machine Learning Algorithms. Tarım Bilimleri Dergisi, Cilt: 29 - Sayı: 2, 427–442. https://ajindex.com/articles/888632

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (3)

  1. Agbola F W, Kelley T G, Bent M J & Rao P P (2002). Eliciting and valuing market preferences with traditional food crops: The case of chickpea in India. The International Food and Agribusiness Management Review 5(1): 7-21. doi.org/10.1016/S1096-7508(02)00110-6
  2. Akpınar Y (2016). Evaluation of soil moisture sensors for soil water content measurement in the Central Anatolian Region. Erciyes University, Graduate School of Natural and Applied Sciences, Master Thesis, Kayseri, Turkey. Ashokkumar K, Diapari M, Jha A B, Tar’an B, Arganosa G & Warkentin T D (2015). Genetic diversity of nutritionally important carotenoids in 94 pea and 121 chickpea accessions. Journal of Food Composition and Analysis 43: 49-60. doi.org/10.1016/j.jfca.2015.04.014 Ataş M, Yardimci Y & Temizel A (2012) A new approach to aflatoxin detection in chili pepper by machine vision. Computers and Electronics in Agriculture 87: 129-141. doi.org/10.1016/j.compag.2012.06.001 Benjamin J G & Nielsen D C (2006). Water deficit effects on root distribution of soybean, field pea and chickpea. Field Crops Research 97(2-3): 248-253. doi.org/10.1016/j.fcr.2005.10.005 Berhane T M, Lane C R, Wu Q, Autrey B C, Anenkhonov O A, Chepinoga V V & Liu H (2018). Decision-tree, rule-based, and random forest classification of high-resolution multispectral imagery for wetland mapping and inventory. Remote Sensing (Basel) 10(4): 580. doi.org/10.3390/rs10040580 Beyaz A, Ozturk R & Turker U (2010). Assessment of mechanical damage on apples with image analysis. Journal: Food, Agriculture and Environment 8(3-4): 476-480. Beyaz A & Ozturk R (2016). Identification of olive cultivars using image processing techniques. Turkish Journal of Agriculture and Forestry 40(5): 671-683. doi.org/10.3906/tar-1504-95 Beyaz A & Gerdan D (2021). Meta-learning-based prediction of different corn cultivars from color feature extraction. Journal of Agricultural Sciences 27(1): 32-41. doi.org/10.15832/ankutbd.567407 Breiman L (2001). Random forests. Machine Learning 45: 5-32. doi.org/10.1023/A:1010933404324 Cetin N, Yaman M, Karaman K & Demir B (2020). Determination of some physicomechanical and biochemical parameters of hazelnut (Corylus avellana L.) cultivars. Turkish Journal of Agriculture and Forestry 44(5): 439-450. doi.org/10.3906/tar-1905-115
  3. Cetin N, Karaman K, Beyzi E, Saglam C & Demirel B (2021). Comparative evaluation of some quality characteristics of sunflower oilseeds (Helianthus annuus L.) through machine learning classifiers. Food